On the use of Kinect depth data for identity, gender and ethnicity classification from facial images

Abstract

This article explores the usefulness of the depth images provided by the current Microsoft Kinect sensors in different face analysis tasks including identity, gender and ethnicity. Four local feature extraction methods (LBP, LPQ, HOG and BSIF) are investigated for both face texture and shape description. Extensive experiments on three publicly available Kinect face databases are reported. The experimental analysis yields into interesting findings. Furthermore, a comprehensive review of the literature on the use of Kinect depth data in face analysis is provided along with the description of the available databases.